susmitm / predictify

A MERN stack based image to text conversion app, which uses Google Cloud Vision to transcribe text from images. Includes User authentication, voice support for transcribed text, user history and responsive UI.

Predictify

Predictify is a A MERN stack based image to text conversion app, which uses Google Cloud Vision to transcribe text from images. Includes User authentication, voice support for transcribed text, user history and responsive UI.

Purpose

The primary purpose of Predictify is to extract text from images using Optical Character Recognition (OCR) technology. It employs AI models, specifically Google Vision, to analyze images and convert the text within them into a readable format.

Demo video

predictify.mp4

Technologies used :

• React JS
• React Context API
• React Router v6
• Google-Vision
• Auth0
• Node.js
• Express.js
• MongoDB
• Chakra UI
• Cloudinary for Image and Video Storage
• Axios
• Vercel for Deployment

Features :

• Authentication

  • Sign-Up
  • Sign-In
  • Logout

• Home Page

  • Upload or Drag and Drop images.

• Result Page

  • Lists the text exacted from the image.
  • Text to Speech for the transcribed text

• History Page

  • Shows the previous predictions made by the user.

Other Features :

• Loaders
• Responsive UI

Join Buzz Social Media today and be a part of an enthusiastic community of creators, influencers, and friends. Connect with the world and express yourself like never before!

Images

• Home Page
• Result Page
• History Page
• Sign In Page
• Sign Up Page